Model save

README.md

@@ -1,10 +1,11 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: microsoft/swin-tiny-patch4-window7-224
 tags:
 - generated_from_trainer
 datasets:
-- image_folder
+- imagefolder
 metrics:
 - accuracy
 model-index:
@@ -14,15 +15,15 @@ model-index:
       name: Image Classification
       type: image-classification
     dataset:
-      name: image_folder
-      type: image_folder
+      name: imagefolder
+      type: imagefolder
       config: default
       split: train
       args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.598512173128945
+      value: 0.7490636704119851
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # swin-tiny-patch4-window7-224-finetuned-mobile-eye-tracking-dataset-v2
 
-This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the image_folder dataset.
+This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6732
-- Accuracy: 0.5985
+- Loss: 0.7276
+- Accuracy: 0.7491
 
 ## Model description
 
@@ -53,35 +54,28 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 256
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- total_train_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 10
+- num_epochs: 3
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6726        | 1.0   | 329  | 0.6758          | 0.5985   |
-| 0.6773        | 2.0   | 658  | 0.6738          | 0.5985   |
-| 0.6701        | 3.0   | 987  | 0.6736          | 0.5985   |
-| 0.6734        | 4.0   | 1317 | 0.6735          | 0.5985   |
-| 0.671         | 5.0   | 1646 | 0.6738          | 0.5985   |
-| 0.6725        | 6.0   | 1975 | 0.6740          | 0.5985   |
-| 0.6702        | 7.0   | 2304 | 0.6737          | 0.5985   |
-| 0.6708        | 8.0   | 2634 | 0.6733          | 0.5983   |
-| 0.6732        | 9.0   | 2963 | 0.6735          | 0.5985   |
-| 0.671         | 9.99  | 3290 | 0.6732          | 0.5985   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.2929        | 0.9811 | 39   | 1.0328          | 0.6404   |
+| 0.9974        | 1.9874 | 79   | 0.7795          | 0.7416   |
+| 0.9114        | 2.9434 | 117  | 0.7276          | 0.7491   |
 
 
 ### Framework versions
 
-- Transformers 4.37.0
-- Pytorch 2.1.2
-- Datasets 2.1.0
-- Tokenizers 0.15.1
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3